can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run GLM-4 9B?

GLM · MIT · estimated for a 141.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at FP16 · 18.8 GB · 124–186 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.1 GB275–413 tok/sRuns great
Q3_K_M4.1 GB255–383 tok/sRuns great
Q4_K_M5.7 GB228–342 tok/sRuns great
Q5_K_M6.7 GB215–322 tok/sRuns great
Q6_K7.8 GB202–302 tok/sRuns great
Q8_010.0 GB179–268 tok/sRuns great
FP1618.8 GB124–186 tok/sRuns great

Ran GLM-4 9B on a NVIDIA H200 (141GB)? Add your real numbers →